Related papers: DI-V2X: Learning Domain-Invariant Representation f…

Vehicle-to-Vehicle technologies have enabled autonomous vehicles to share information to see through occlusions, greatly enhancing perception performance. Nevertheless, existing works all focused on homogeneous traffic where vehicles are…

A key challenge for autonomous driving lies in maintaining real-time situational awareness regarding surrounding obstacles under strict latency constraints. The high processing requirements coupled with limited onboard computational…

Recent progress in in-context reinforcement learning (ICRL) has demonstrated its potential for training generalist agents that can acquire new tasks directly at inference. Algorithm Distillation (AD) pioneered this paradigm and was…

Knowledge Distillation (KD) for object detection aims to train a compact detector by transferring knowledge from a teacher model. Since the teacher model perceives data in a way different from humans, existing KD methods only distill…

Contrastive image-to-LiDAR knowledge transfer, commonly used for learning 3D representations with synchronized images and point clouds, often faces a self-conflict dilemma. This issue arises as contrastive losses unintentionally dissociate…

Accurate 3D object detection for autonomous driving requires complementary sensors. Cameras provide dense semantics but unreliable depth, while millimeter-wave radar offers precise range and velocity measurements with sparse geometry. We…

Multimodal image matching seeks pixel-level correspondences between images of different modalities, crucial for cross-modal perception, fusion and analysis. However, the significant appearance differences between modalities make this task…

Large-scale diffusion models have made significant advances in image generation, particularly through cross-attention mechanisms. While cross-attention has been well-studied in text-to-image tasks, their interpretability in image-to-image…

Multi-agent collaborative perception has emerged as a widely recognized technology in the field of autonomous driving in recent years. However, current collaborative perception predominantly relies on LiDAR point clouds, with significantly…

Knowledge distillation is an attractive approach for learning compact deep neural networks, which learns a lightweight student model by distilling knowledge from a complex teacher model. Attention-based knowledge distillation is a specific…

Visuomotor policies often leverage large pre-trained Vision Transformers (ViTs) for their powerful generalization capabilities. However, their significant data requirements present a major challenge in the data-scarce context of most…

We consider the problem of domain generalization, namely, how to learn representations given data from a set of domains that generalize to data from a previously unseen domain. We propose the Domain Invariant Variational Autoencoder (DIVA),…

Employing Vehicle-to-Vehicle communication to enhance perception performance in self-driving technology has attracted considerable attention recently; however, the absence of a suitable open dataset for benchmarking algorithms has made it…

This work introduces RGBX-DiffusionDet, an object detection framework extending the DiffusionDet model to fuse the heterogeneous 2D data (X) with RGB imagery via an adaptive multimodal encoder. To enable cross-modal interaction, we design…

The huge research interest in cellular vehicle-to-everything (C-V2X) communications in recent days is attributed to their ability to schedule multiple access more efficiently as compared to its predecessor technology, i.e., dedicated…

In recent years, current mainstream feature masking distillation methods mainly function by reconstructing selectively masked regions of a student network from the feature maps of a teacher network. In these methods, attention mechanisms…

Due to the limitations of a single autonomous vehicle, Cellular Vehicle-to-Everything (C-V2X) technology opens a new window for achieving fully autonomous driving through sensor information sharing. However, real-world datasets supporting…

Continual learning seeks to maintain stable adaptation under non-stationary environments, yet this problem becomes particularly challenging in object detection, where most existing methods implicitly assume relatively balanced visual…

Deep Metric Learning (DML) plays an important role in modern computer vision research, where we learn a distance metric for a set of image representations. Recent DML techniques utilize the proxy to interact with the corresponding image…

We address the challenging problem of learning motion representations using deep models for video recognition. To this end, we make use of attention modules that learn to highlight regions in the video and aggregate features for…